paper-with-me

Papers

Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech Detection

2022-05-09 · NAACL 2022 7 · Indira Sen, Mattia Samory, Claudia Wagner, Isabelle Augenstein

Counterfactually Augmented Data (CAD) aims to improve out-of-domain generalizability, an indicator of model robustness. The improvement is credited with promoting core features of the construct over spurious artifacts that happen to correlate with it. Yet, over-relying on core features may lead to unintended model bias. Especially, construct-driven CAD -- perturbations of core features -- may induce models to ignore the context in which core features are used. Here, we test models for sexism and hate speech detection on challenging data: non-hateful and non-sexist usage of identity and gendered terms. In these hard cases, models trained on CAD, especially construct-driven CAD, show higher false-positive rates than models trained on the original, unperturbed data. Using a diverse set of CAD -- construct-driven and construct-agnostic -- reduces such unintended bias.

📄 PDF Abstract BibTeX arXiv:2205.04238

Code (0)

등록된 구현이 없습니다.

Tasks

Hate Speech Detection

Similar Papers 제목 키워드 기반

Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data

2024-07-18 · Wufei Ma, Kai Li, Zhongshi Jiang, Moustafa Meshry 외

Recent video-text foundation models have demonstrated strong performance on a wide variety of downstream video understanding tasks. Can these video-text models genuinely understand the contents of natural videos? Standar…

Language ModellingLarge Language ModelRetrievalVideo Understanding

PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning

2024-06-09 · Xiaoqi Qiu, Yongjie Wang, Xu Guo, Zhiwei Zeng 외

Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Training with CAD enhances model robu…

Contrastive Learningcounterfactual

Sustainable Modular Debiasing of Language Models

2021-09-08 · Findings (EMNLP) 2021 11 · Anne Lauscher, Tobias Lüken, Goran Glavaš

Unfair stereotypical biases (e.g., gender, racial, or religious biases) encoded in modern pretrained language models (PLMs) have negative ethical implications for widespread adoption of state-of-the-art language technolo…

FairnessLanguage ModelingLanguage Modelling

Counterfactually-Augmented SNLI Training Data Does Not Yield Better Generalization Than Unaugmented Data

2020-10-09 · EMNLP (insights) 2020 11 · William Huang, Haokun Liu, Samuel R. Bowman

A growing body of work shows that models exploit annotation artifacts to achieve state-of-the-art performance on standard crowdsourced benchmarks---datasets collected from crowdworkers to create an evaluation task---whil…

counterfactualNatural Language InferenceNatural Language UnderstandingReading Comprehension

Limitations of Pinned AUC for Measuring Unintended Bias

2019-03-05 · Daniel Borkan, Lucas Dixon, John Li, Jeffrey Sorensen 외

This report examines the Pinned AUC metric introduced and highlights some of its limitations. Pinned AUC provides a threshold-agnostic measure of unintended bias in a classification model, inspired by the ROC-AUC metric.…

General Classification